Merge pull request #1014 from Sage-Bionetworks/develop

Release 22.11.2

Author: linglp

.github/workflows/test.yml

@@ -118,7 +118,7 @@ jobs:
         run: >
           source .venv/bin/activate;
           pytest --cov-report=term --cov-report=html:htmlcov --cov=schematic/
-          -m "not (google_credentials_needed or rule_combos)"
+          -m "not (google_credentials_needed or rule_combos or schematic_api)"
     
       - name: Upload pytest test results
         uses: actions/upload-artifact@v2

README.md

@@ -74,7 +74,7 @@ This command will install the dependencies based on what we specify in poetry.lo
 5. Fill in credential files: 
 *Note*: If you won't interact with Synapse, please ignore this section.
 
-There are two main configuration files that need to be edited :
+There are two main configuration files that need to be edited:
 [config.yml](https://github.com/Sage-Bionetworks/schematic/blob/develop/config.yml)
 and [synapseConfig](https://raw.githubusercontent.com/Sage-Bionetworks/synapsePythonClient/v2.3.0-rc/synapseclient/.synapseConfig)
 
@@ -88,6 +88,8 @@ editor of your choice and edit the `username` and `authtoken` attribute under th
 
 <strong>Configure config.yml File</strong>
 
+*Note*: Below is only a brief explanation of some attributes in `config.yml`. <strong>Please use the link [here](https://github.com/Sage-Bionetworks/schematic/blob/develop/config.yml) to get the latest version of `config.yml` in `develop` branch</strong>.
+
 Description of `config.yml` attributes
 
     definitions:
@@ -104,20 +106,39 @@ Description of `config.yml` attributes
         service_acct_creds: "syn25171627" # synapse ID of service_account_creds.json file
 
     manifest:
-        title: "Patient Manifest " # title of metadata manifest file
-        data_type: "Patient" # component or data type from the data model
+        title: "example" # title of metadata manifest file
+        # to make all manifests enter only 'all manifests'
+        data_type: 
+          - "Biospecimen"
+          - "Patient"
 
     model:
         input:
             location: "data/schema_org_schemas/example.jsonld" # path to JSON-LD data model
             file_type: "local" # only type "local" is supported currently
-            validation_schema: "~/path/to/validation_schema.json" # path to custom JSON Validation Schema JSON file
-            log_location: "~/path/to/log_folder/validation_schema.json" # auto-generated JSON Validation Schemas can be logged
-        
+    style: # configuration of google sheet
+        google_manifest:
+          req_bg_color:
+            red: 0.9215
+            green: 0.9725
+            blue: 0.9803
+          opt_bg_color:
+            red: 1.0
+            green: 1.0
+            blue: 0.9019
+          master_template_id: '1LYS5qE4nV9jzcYw5sXwCza25slDfRA1CIg3cs-hCdpU'
+          strict_validation: true
 
 *Note*: Paths can be specified relative to the `config.yml` file or as absolute paths.
 
-6. Obtain Google credential Files
+6. Login to Synapse by using the command line
+On the CLI in your virtual environment, run the following command: 
+```
+synapse login -u <synapse username> -p <synapse password> --rememberMe
+```
+Please make sure that you run the command before running `schematic init` below
+
+7. Obtain Google credential Files
 
 To obtain ``credentials.json`` and ``token.pickle``, please run:
 
@@ -152,7 +173,6 @@ requires token-based authentication. As browser support that requires the token-
 token-based authentication and keep only service account authentication in the future. 
 
 
-
 ### Development process instruction
 
 For new features, bugs, enhancements

api/openapi/api.yaml

@@ -79,11 +79,22 @@ paths:
             nullable: true
           description: ID of view listing all project data assets. E.g. for Synapse this would be the Synapse ID of the fileview listing all data assets for a given project.(i.e. master_fileview in config.yml)
           required: false
+        - in: query
+          name: output_format
+          schema:
+            type: string
+            enum: ["excel", "google_sheet", "dataframe (only if getting existing manifests)"]
+          description: If "excel" gets selected, this approach would avoid sending metadata to Google sheet APIs; if "google_sheet" gets selected, this would return a Google sheet URL. This parameter could potentially override sheet_url parameter. 
+          required: false
       operationId: api.routes.get_manifest_route
       responses:
-        "201":
-          description: Googlesheet link created
+        "200":
+          description: Googlesheet link created OR an excel file gets returned OR pandas dataframe gets returned
           content:
+            application/vnd.ms-excel:
+              schema:
+                type: string
+                format: binary
             application/json:
               schema:
                 type: string
@@ -381,6 +392,13 @@ paths:
           description: Title of Manifest
           example: Example
           required: false
+        - in: query
+          name: return_excel
+          schema:
+            type: boolean
+            nullable: true
+          description: If true, this would return an Excel spreadsheet.(This approach would avoid sending metadata to Google sheet APIs)
+          required: false
       operationId: api.routes.populate_manifest_route
       responses:
         "200":

api/routes.py

@@ -7,7 +7,7 @@
 
 import connexion
 from connexion.decorators.uri_parsing import Swagger2URIParser
-from flask import current_app as app, request, g, jsonify
+from flask import current_app as app
 from werkzeug.debug import DebuggedApplication
 
 from schematic import CONFIG
@@ -25,6 +25,7 @@
 import json
 from schematic.utils.df_utils import load_df
 import pickle
+from flask import send_from_directory
 
 # def before_request(var1, var2):
 #     # Do stuff before your route executes
@@ -196,7 +197,20 @@ def get_temp_jsonld(schema_url):
     return tmp_file.name
 
 # @before_request
-def get_manifest_route(schema_url, title, oauth, use_annotations, dataset_ids=None, asset_view = None):
+def get_manifest_route(schema_url: str, oauth: bool, use_annotations: bool, dataset_ids=None, asset_view = None, output_format=None, title=None):
+    """Get the immediate dependencies that are related to a given source node.
+        Args:
+            schema_url: link to data model in json ld format
+            title: title of a given manifest. 
+            oauth: if user wants to use OAuth for Google authentication
+            dataset_id: Synapse ID of the "dataset" entity on Synapse (for a given center/project).
+            output_format: contains three option: "excel", "google_sheet", and "dataframe". if set to "excel", return an excel spreadsheet
+            use_annotations: Whether to use existing annotations during manifest generation
+            asset_view: ID of view listing all project data assets. For example, for Synapse this would be the Synapse ID of the fileview listing all data assets for a given project.
+        Returns:
+            Googlesheet URL (if sheet_url is True), or pandas dataframe (if sheet_url is False).
+    """
+
     # call config_handler()
     config_handler(asset_view = asset_view)
 
@@ -238,20 +252,32 @@ def get_manifest_route(schema_url, title, oauth, use_annotations, dataset_ids=No
                 )
 
 
-    def create_single_manifest(data_type, dataset_id=None):
+    def create_single_manifest(data_type, title, dataset_id=None, output_format=None):
         # create object of type ManifestGenerator
         manifest_generator = ManifestGenerator(
             path_to_json_ld=jsonld,
-            title=t,
+            title=title,
             root=data_type,
             oauth=oauth,
             use_annotations=use_annotations,
             alphabetize_valid_values = 'ascending',
         )
 
+        # if returning a dataframe
+        if output_format:
+            if "dataframe" in output_format:
+                output_format = "dataframe"
+
         result = manifest_generator.get_manifest(
-            dataset_id=dataset_id, sheet_url=True,
+            dataset_id=dataset_id, sheet_url=True, output_format=output_format
         )
+
+        # return an excel file if output_format is set to "excel"
+        if output_format == "excel":
+            dir_name = os.path.dirname(result)
+            file_name = os.path.basename(result)
+            mimetype='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
+            return send_from_directory(directory=dir_name, filename=file_name, as_attachment=True, mimetype=mimetype, cache_timeout=0)
 
         return result
 
@@ -262,22 +288,37 @@ def create_single_manifest(data_type, dataset_id=None):
         component_digraph = sg.se.get_digraph_by_edge_type('requiresComponent')
         components = component_digraph.nodes()
         for component in components:
-            t = f'{title}.{component}.manifest'
-            result = create_single_manifest(data_type = component)
-            all_results.append(result)
+            if title:
+                t = f'{title}.{component}.manifest'
+            else: 
+                t = f'Example.{component}.manifest'
+            if output_format != "excel":
+                result = create_single_manifest(data_type=component, output_format=output_format, title=t)
+                all_results.append(result)
+            else: 
+                app.logger.error('Currently we do not support returning multiple files as Excel format at once. Please choose a different output format. ')
     else:
         for i, dt in enumerate(data_type):
-            if len(data_type) > 1:
-                t = f'{title}.{dt}.manifest'
-            else:
-                t = title
-
+            if not title: 
+                t = f'Example.{dt}.manifest'
+            else: 
+                if len(data_type) > 1:
+                    t = f'{title}.{dt}.manifest'
+                else: 
+                    t = title
             if dataset_ids:
                 # if a dataset_id is provided add this to the function call.
-                result = create_single_manifest(data_type = dt, dataset_id = dataset_ids[i])
+                result = create_single_manifest(data_type=dt, dataset_id=dataset_ids[i], output_format=output_format, title=t)
             else:
-                result = create_single_manifest(data_type = dt)
-            all_results.append(result)
+                result = create_single_manifest(data_type=dt, output_format=output_format, title=t)
+
+            # if output is pandas dataframe or google sheet url
+            if isinstance(result, str) or isinstance(result, pd.DataFrame):
+                all_results.append(result)
+            else: 
+                if len(data_type) > 1:
+                    app.logger.warning(f'Currently we do not support returning multiple files as Excel format at once. Only {t} would get returned. ')
+                return result
 
     return all_results
 
@@ -341,7 +382,7 @@ def submit_manifest_route(schema_url, asset_view=None, manifest_record_type=None
 
     return manifest_id
 
-def populate_manifest_route(schema_url, title=None, data_type=None):
+def populate_manifest_route(schema_url, title=None, data_type=None, return_excel=None):
     # call config_handler()
     config_handler()
 
@@ -355,7 +396,7 @@ def populate_manifest_route(schema_url, title=None, data_type=None):
     metadata_model = MetadataModel(inputMModelLocation=jsonld, inputMModelLocationType='local')
 
     #Call populateModelManifest class
-    populated_manifest_link = metadata_model.populateModelManifest(title=title, manifestPath=temp_path, rootNode=data_type)
+    populated_manifest_link = metadata_model.populateModelManifest(title=title, manifestPath=temp_path, rootNode=data_type, return_excel=return_excel)
 
     return populated_manifest_link
 

pyproject.toml

@@ -112,6 +112,10 @@ filterwarnings = [
 markers = [
     """\
     google_credentials_needed: marks tests requiring \
-    Google credentials (skipped on GitHub CI)\
+    Google credentials (skipped on GitHub CI) \
     """,
+    """\
+    schematic_api: marks tests requiring \
+    running API locally (skipped on GitHub CI)   
+    """
 ]

schematic/manifest/commands.py

@@ -1,6 +1,6 @@
 import os
 import logging
-
+from pathlib import Path
 import click
 import click_log
 import logging
@@ -12,7 +12,7 @@
 from schematic.help import manifest_commands
 from schematic import CONFIG
 from schematic.schemas.generator import SchemaGenerator
-from schematic.utils.google_api_utils import export_manifest_csv, export_manifest_excel
+from schematic.utils.google_api_utils import export_manifest_csv, export_manifest_excel, export_manifest_drive_service
 from schematic.store.synapse import SynapseStorage
 
 logger = logging.getLogger(__name__)
@@ -147,8 +147,26 @@ def create_single_manifest(data_type, output_csv=None, output_xlsx=None):
         )
 
         # call get_manifest() on manifest_generator
+        # if output_xlsx gets specified, output_format = "excel"
+        if output_xlsx: 
+            output_format = "excel"
+
+            # if file name is in the path, and that file does not exist
+            if not os.path.exists(output_xlsx):
+                if ".xlsx" or ".xls" in output_xlsx:
+                    path = Path(output_xlsx)
+                    output_path = path.parent.absolute()
+                else: 
+                    logger.error(f"{output_xlsx} does not exists. Please try a valid file path")
+
+            else: 
+                output_path = output_xlsx
+        else: 
+            output_format = None
+            output_path = None
+
         result = manifest_generator.get_manifest(
-            dataset_id=dataset_id, sheet_url=sheet_url, json_schema=json_schema,
+            dataset_id=dataset_id, sheet_url=sheet_url, json_schema=json_schema, output_format = output_format, output_path = output_path
         )
 
         if sheet_url:
@@ -160,13 +178,13 @@ def create_single_manifest(data_type, output_csv=None, output_xlsx=None):
             if prefix_ext == ".model":
                 prefix = prefix_root
             output_csv = f"{prefix}.{data_type}.manifest.csv"
+
         elif output_xlsx:
-            export_manifest_excel(output_excel=output_xlsx, manifest=result)
             logger.info(
                 f"Find the manifest template using this Excel file path: {output_xlsx}"
             )
             return result
-        export_manifest_csv(file_name=output_csv, manifest=result)
+        export_manifest_csv(file_path=output_csv, manifest=result)
         logger.info(
                 f"Find the manifest template using this CSV file path: {output_csv}"
             )
@@ -184,8 +202,12 @@ def create_single_manifest(data_type, output_csv=None, output_xlsx=None):
             result = create_single_manifest(data_type = component)
     else:
         for dt in data_type:
-            if len(data_type) > 1:
+            if len(data_type) > 1 and not output_xlsx:
                 t = f'{title}.{dt}.manifest'
+            elif output_xlsx: 
+                if ".xlsx" or ".xls" in output_xlsx:
+                    title_with_extension = os.path.basename(output_xlsx)
+                    t = title_with_extension.split('.')[0]
             else:
                 t = title
             result = create_single_manifest(data_type = dt, output_csv=output_csv, output_xlsx=output_xlsx)